Delete 'danmaku_analyzer.py'

5 months ago · c17dc71935
parent 39ff70d51b
commit c17dc71935
1 changed files with 0 additions and 93 deletions
--- a/danmaku_analyzer.py
+++ b/danmaku_analyzer.py
@ -1,93 +0,0 @@
-from collections import Counter
-import pandas as pd
-
-class DanmakuAnalyzer:
-    def __init__(self, danmakus):
-        self.danmakus = [d.strip() for d in danmakus if d.strip()]
-        self.stopwords = self.load_stopwords()
-    
-    def load_stopwords(self):
-        """加载停用词"""
-        try:
-            with open("stopwords.txt", "r", encoding="utf-8") as f:
-                return set([line.strip() for line in f.readlines()])
-        except:
-            # 默认停用词
-            return set(["的", "了", "是", "在", "我", "有", "和", "就", "不", "人", "都", "一", "一个", "上", "也", "很", "到", "说", "要", "去", "你", "会", "着", "没有", "看", "好", "自己", "这"])
-    
-    def count_danmakus(self):
-        """统计弹幕数量"""
-        # 过滤与AI技术应用无关的弹幕
-        ai_related_words = ["AI", "人工智能", "大模型", "语言模型", "LLM", "训练", "算法", "数据", "应用", "成本", "效率", "伦理", "隐私", "安全", "未来", "发展", "编程", "创作", "教育"]
-        ai_danmakus = [d for d in self.danmakus if any(word in d for word in ai_related_words)]
-        
-        # 统计所有弹幕
-        all_counter = Counter(self.danmakus)
-        # 统计AI相关弹幕
-        ai_counter = Counter(ai_danmakus)
-        
-        return all_counter, ai_counter
-    
-    def save_to_excel(self, ai_counter, filename="弹幕统计.xlsx"):
-        """保存统计结果到Excel"""
-        # 转换为DataFrame
-        df = pd.DataFrame(ai_counter.most_common(), columns=["弹幕内容", "出现次数"])
-        # 保存到Excel
-        df.to_excel(filename, index=False)
-        print(f"统计结果已保存到{filename}")
-        return df
-    
-    def get_main_views(self, ai_counter):
-        """分析用户主流看法"""
-        # 分类关键词
-        cost_related = ["成本", "价格", "费用", "免费", "付费"]
-        application_related = ["应用", "使用", "场景", "领域", "行业", "教育", "医疗", "工作", "创作", "编程"]
-        negative_related = ["风险", "危险", "伦理", "隐私", "安全", "失业", "替代", "问题"]
-        positive_related = ["方便", "高效", "厉害", "强大", "有用", "帮助", "进步"]
-        
-        # 统计各类别弹幕
-        categories = {
-            "应用成本": 0,
-            "应用领域": 0,
-            "不利影响": 0,
-            "积极影响": 0,
-            "其他观点": 0
-        }
-        
-        for danmaku, count in ai_counter.items():
-            matched = False
-            for word in cost_related:
-                if word in danmaku:
-                    categories["应用成本"] += count
-                    matched = True
-                    break
-            if matched:
-                continue
-                
-            for word in application_related:
-                if word in danmaku:
-                    categories["应用领域"] += count
-                    matched = True
-                    break
-            if matched:
-                continue
-                
-            for word in negative_related:
-                if word in danmaku:
-                    categories["不利影响"] += count
-                    matched = True
-                    break
-            if matched:
-                continue
-                
-            for word in positive_related:
-                if word in danmaku:
-                    categories["积极影响"] += count
-                    matched = True
-                    break
-            if matched:
-                continue
-                
-            categories["其他观点"] += count
-        
-        return categories